# Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing

arXiv: https://arxiv.org/abs/2402.19298 · HTML: https://mlsanity.com/paper/2402.19298/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 67 references that are in the map.
- First posted on arXiv 29 Feb 2024.

## Builds on (most cited first, 12 of 12)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Provable Dynamic Fusion for Low-Quality Multimodal Data](https://mlsanity.com/paper/2306.02050/) (2023)
- [Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing](https://mlsanity.com/paper/2302.05744/) (2023)
- [S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens](https://mlsanity.com/paper/2309.04038/) (2023)
- [Visual Prompt Flexible-Modal Face Anti-Spoofing](https://mlsanity.com/paper/2307.13958/) (2023)
- [M3FAS: An Accurate and Robust MultiModal Mobile Face Anti-Spoofing System](https://mlsanity.com/paper/2301.12831/) (2023)
- [Exposing Image Splicing Traces in Scientific Publications via Uncertainty-guided Refinement](https://mlsanity.com/paper/2309.16388/) (2023)
- [Uncertainty-Aware Physically-Guided Proxy Tasks for Unseen Domain Face Anti-spoofing](https://mlsanity.com/paper/2011.14054/) (2020)
- [Adapting Neural Models with Sequential Monte Carlo Dropout](https://mlsanity.com/paper/2210.15779/) (2022)

## Built on by (most cited first, 16 of 16)

- [Deep Multimodal Learning with Missing Modality: A Survey](https://mlsanity.com/paper/2409.07825/) (2024)
- [Test-Time Domain Generalization for Face Anti-Spoofing](https://mlsanity.com/paper/2403.19334/) (2024)
- [Towards Data-Centric Face Anti-Spoofing: Improving Cross-domain Generalization via Physics-based Data Synthesis](https://mlsanity.com/paper/2409.03501/) (2024)
- [Multi-modal Knowledge Distillation-based Human Trajectory Forecasting](https://mlsanity.com/paper/2503.22201/) (2025)
- [Domain Generalization for Face Anti-spoofing via Content-aware Composite Prompt Engineering](https://mlsanity.com/paper/2504.04470/) (2025)
- [DADM: Dual Alignment of Domain and Modality for Face Anti-spoofing](https://mlsanity.com/paper/2503.00429/) (2025)
- [FA^{3}-CLIP: Frequency-Aware Cues Fusion and Attack-Agnostic Prompt Learning for Unified Face Attack Detection](https://mlsanity.com/paper/2504.00454/) (2025)
- [SAMSOD: Rethinking SAM Optimization for RGB-T Salient Object Detection](https://mlsanity.com/paper/2510.03689/) (2025)
- [Decoding Visual Neural Representations by Multimodal with Dynamic Balancing](https://mlsanity.com/paper/2509.03433/) (2025)
- [Multi-View Slot Attention Using Paraphrased Texts for Face Anti-Spoofing](https://mlsanity.com/paper/2509.06336/) (2025)
- [A Multi-Modal Approach for Face Anti-Spoofing in Non-Calibrated Systems using Disparity Maps](https://mlsanity.com/paper/2410.24031/) (2024)
- [Multi-Modal Face Anti-Spoofing via Cross-Modal Feature Transitions](https://mlsanity.com/paper/2507.05575/) (2025)
- [AI-driven Remote Facial Skin Hydration and TEWL Assessment from Selfie Images: A Systematic Solution](https://mlsanity.com/paper/2509.06282/) (2025)
- [Robust Multi-Modal Face Anti-Spoofing with Domain Adaptation: Tackling Missing Modalities, Noisy Pseudo-Labels, and Model Degradation](https://mlsanity.com/paper/2509.23475/) (2025)
- [StegaFFD: Privacy-Preserving Face Forgery Detection via Fine-Grained Steganographic Domain Lifting](https://mlsanity.com/paper/2603.02886/) (2026)
- [MMDG-Bench: A Benchmark for Multimodal Domain Generalization](https://mlsanity.com/paper/2606.00891/) (2026)

## Abstract (arXiv)

Face Anti-Spoofing (FAS) is crucial for securing face recognition systems against presentation attacks. With advancements in sensor manufacture and multi-modal learning techniques, many multi-modal FAS approaches have emerged. However, they face challenges in generalizing to unseen attacks and deployment conditions. These challenges arise from (1) modality unreliability, where some modality sensors like depth and infrared undergo significant domain shifts in varying environments, leading to the spread of unreliable information during cross-modal feature fusion, and (2) modality imbalance, where training overly relies on a dominant modality hinders the convergence of others, reducing effectiveness against attack types that are indistinguishable sorely using the dominant modality. To address modality unreliability, we propose the Uncertainty-Guided Cross-Adapter (U-Adapter) to recognize unreliably detected regions within each modality and suppress the impact of unreliable regions on other modalities. For modality imbalance, we propose a Rebalanced Modality Gradient Modulation (ReGrad) strategy to rebalance the convergence speed of all modalities by adaptively adjusting their gradients. Besides, we provide the first large-scale benchmark for evaluating multi-modal FAS performance under domain generalization scenarios. Extensive experiments demonstrate that our method outperforms state-of-the-art methods. Source code and protocols will be released on https://github.com/OMGGGGG/mmdg.